Optimal Intrusion Response
An OpenAI Gym interface to a MDP/Markov Game model for optimal intrusion response of a realistic infrastructure simulated using system traces.
Included Environments
optimal-intrusion-response-v1optimal-intrusion-response-v2optimal-intrusion-response-v3
Requirements
- Python 3.5+
- OpenAI Gym
- NumPy
- jsonpickle (for configuration files)
- torch (for baseline algorithms)
Installation
# install from pip
pip install gym-optimal-intrusion-response==1.0.0
# local install from source
$ pip install -e gym-optimal-intrusion-response
# force upgrade deps
$ pip install -e gym-optimal-intrusion-response --upgrade
# git clone and install from source
git clone https://github.com/Limmen/gym-optimal-intrusion-response
cd gym-optimal-intrusion-response
pip3 install -e .
Usage
The environment can be accessed like any other OpenAI environment with gym.make. Once the environment has been created, the API functions step(), reset(), render(), and close() can be used to train any RL algorithm of your preference.
import gym
from gym_idsgame.envs import IdsGameEnv
env_name = "optimal-intrusion-response-v1"
env = gym.make(env_name)
Infrastructure
Traces
Alert/login traces from the emulated infrastructure are available in (./traces).
Publications
@INPROCEEDINGS{hammar_stadler_cnsm_21,
AUTHOR="Kim Hammar and Rolf Stadler",
TITLE="Learning Intrusion Prevention Policies through Optimal Stopping",
BOOKTITLE="International Conference on Network and Service Management (CNSM 2021)",
ADDRESS="Izmir, Turkey",
DAYS=1,
YEAR=2021,
note={\url{http://dl.ifip.org/db/conf/cnsm/cnsm2021/1570732932.pdf}},
KEYWORDS="Network Security, automation, optimal stopping, reinforcement learning, Markov Decision Processes",
ABSTRACT="We study automated intrusion prevention using reinforcement learning. In a novel approach, we formulate the problem of intrusion prevention as an optimal stopping problem. This formulation allows us insight into the structure of the optimal policies, which turn out to be threshold based. Since the computation of the optimal defender policy using dynamic programming is not feasible for practical cases, we approximate the optimal policy through reinforcement learning in a simulation environment. To define the dynamics of the simulation, we emulate the target infrastructure and collect measurements. Our evaluations show that the learned policies are close to optimal and that they indeed can be expressed using thresholds."
}
@INPROCEEDINGS{Hamm2011:Finding,
AUTHOR="Kim Hammar and Rolf Stadler",
TITLE="Finding Effective Security Strategies through Reinforcement Learning and
{Self-Play}",
BOOKTITLE="International Conference on Network and Service Management (CNSM 2020)
(CNSM 2020)",
ADDRESS="Izmir, Turkey",
DAYS=1,
MONTH=nov,
YEAR=2020,
KEYWORDS="Network Security; Reinforcement Learning; Markov Security Games",
ABSTRACT="We present a method to automatically find security strategies for the use
case of intrusion prevention. Following this method, we model the
interaction between an attacker and a defender as a Markov game and let
attack and defense strategies evolve through reinforcement learning and
self-play without human intervention. Using a simple infrastructure
configuration, we demonstrate that effective security strategies can emerge
from self-play. This shows that self-play, which has been applied in other
domains with great success, can be effective in the context of network
security. Inspection of the converged policies show that the emerged
policies reflect common-sense knowledge and are similar to strategies of
humans. Moreover, we address known challenges of reinforcement learning in
this domain and present an approach that uses function approximation, an
opponent pool, and an autoregressive policy representation. Through
evaluations we show that our method is superior to two baseline methods but
that policy convergence in self-play remains a challenge."
}
@misc{hammar2021intrusion,
title={Intrusion Prevention through Optimal Stopping},
author={Kim Hammar and Rolf Stadler},
year={2021},
eprint={2111.00289},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
See also
Author & Maintainer
Kim Hammar [email protected]
Copyright and license
Creative Commons
(C) 2021, Kim Hammar
33 Dec 20, 2022
1 Feb 12, 2022
1.7k Dec 31, 2022
217 Jan 3, 2023
40 Dec 24, 2022
416 Jan 9, 2023
117 Dec 28, 2022
80 Dec 21, 2022
1 Mar 28, 2022
24 Nov 03, 2022
38 Dec 12, 2022
7 Jul 10, 2022
2 Mar 21, 2022
46 Dec 07, 2022
101 Jan 01, 2023
27 May 09, 2022
676 Dec 31, 2022
0 Nov 17, 2022
10 May 18, 2022
1.7k Dec 24, 2022
98 Nov 10, 2022
11 Oct 18, 2022
912 Jan 08, 2023
9 Feb 15, 2022
27 Aug 08, 2022
72 Nov 09, 2022
7 Sep 21, 2022
29 Dec 05, 2022
20.6k Jan 09, 2023